Speech enhancement method with geometric phase estimation by incorporating MIXMAX model

In this paper, we propose a frequency-domain speech enhancement algorithm with phase estimation, in which the speech model is modeled by a Gaussian mixture model (GMM) in the log-spectral domain and two closed-form log-spectral amplitude estimators for speech and noise are derived directly by using a Mixture-Maximum (MIXMAX) model. Because the accurate estimation of speech phase could help to reduce the undesired noise residues in the enhanced signal, our two log-spectral estimators are also used to construct a geometric approach for phase estimation in each frequency bin. In order to solve the ambiguity problem in phase estimation, we utilize the complex linear predictive analysis (CLPA) and inconsistency constraint to find an appropriate phase. Experimental results show that, in comparison with the reference methods, the proposed method achieves an efficient improvement in speech quality.